Service status.
We check the website, the API, the chat, the CLI sign-in, the docs and every public model once a minute. Each bar is one day of measured uptime. Days we did not measure stay empty.
All systems operational
Refreshes every minute.
Use the arrow keys to read each day.
Platform
Website
Site, console and account pages
- 90-day uptime
- 100.00%
- Latency
- 138 ms
Operational
API
/v1 endpoints and the model list
- 90-day uptime
- 100.00%
- Latency
- 135 ms
Operational
Chat
Research chat and its tools
- 90-day uptime
- 100.00%
- Latency
- 110 ms
Operational
CLI sign-in
Device sign-in behind notholy login
- 90-day uptime
- 100.00%
- Latency
- 43 ms
Operational
Docs
Documentation site
- 90-day uptime
- 100.00%
- Latency
- 96 ms
Operational
Models
A model counts as up when the gateway has a healthy route for it. The probe sends no prompts, so this reflects route configuration and recent request errors.
NotHoly Specter
- 90-day uptime
- 100.00%
Operational
NotHoly Pulse Flash
- 90-day uptime
- 99.92%
Operational
NotHoly Vector Flash 1017
- 90-day uptime
- 100.00%
Operational
NotHoly Wisp Flash
- 90-day uptime
- 100.00%
Operational
Bar colors
- 99.9% or more
- 98% to 99.9%
- Below 98%
- No data
Measuring since Nov 7, 2026. Days before that show no data.
Past incidents
Resolved in the last 30 days.
No incidents in the last 30 days.